A data-driven temperature compensation method and system for a numerical control machine tool

Abstract

The application relates to the technical field of numerical control machine tool control, in particular to a data-driven numerical control machine tool temperature compensation method and system, which comprises the following steps: respectively comparing the difference between the temperature data variation trend and the amplitude at a temperature measuring point and a homologous measuring point, combining the similarity between the temperature data autocorrelation degree at the temperature measuring point and the homologous measuring point to obtain the temperature interference degree, combining the correlation degree between the displacement data of the main shaft of the numerical control machine tool in the main direction and the temperature data of any homologous measuring point of each temperature measuring point at all collection time points to determine the temperature weight coefficient, and compensating the temperature of the numerical control machine tool at the current time. The application aims to improve the accuracy of numerical control machine tool temperature compensation.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of numerical control machine tool control, in particular to a numerical control machine tool temperature compensation method and system using data driving. BACKGROUND

[0002] The numerical control machine tool is an automatic machine tool equipped with a program control system and is an important component of an industrial control system. The numerical control machine tool can automatically complete a machining task on a workpiece according to a pre-prepared program, accurately control the movement of the machine tool, and thus improve the production efficiency and machining quality of the workpiece.

[0003] The numerical control machine tool generates a large amount of heat during machining, which causes the temperature of each component of the machine tool to rise and thermal deformation to occur. Since each component of the machine tool has a different thermal expansion coefficient, the change in temperature causes the geometric shape of the machine tool to change, which in turn affects the machining precision of the workpiece. Therefore, a temperature compensation method needs to be used to reduce the influence of thermal deformation of the machine tool on the overall machining precision of the workpiece. The traditional numerical control machine tool temperature compensation method obtains the temperature values of multiple positions on the numerical control machine tool, and calculates a temperature compensation result according to the mean value of all the obtained temperature values. However, this method does not consider the different influences of the temperature changes at different positions in the numerical control machine tool on the thermal deformation of the machine tool and the influences of external interference possibly received by the temperature during data collection, so that the mean value of all the obtained temperature values cannot accurately reflect the thermal deformation of the machine tool, which in turn affects the precision of the temperature compensation result of the machine tool. SUMMARY

[0004] To solve the above technical problems, the purpose of the present application is to provide a numerical control machine tool temperature compensation method and system using data driving, and the technical solution adopted is as follows:

[0005] In the first aspect, the present application provides a numerical control machine tool temperature compensation method using data driving, which comprises the following steps:

[0006] A plurality of temperature measuring points are arranged on the numerical control machine tool, and the temperature data of each temperature measuring point at all collection time points within a preset time length before the current time and the displacement data of the main shaft of the numerical control machine tool in each direction are obtained;

[0007] All the temperature measuring points are clustered, all the temperature measuring points in the cluster cluster where each temperature measuring point is located are recorded as homologous measuring points of each temperature measuring point, the differences between all the temperature data in the neighborhood of each collection time point at each temperature measuring point and its respective homologous measuring points and the differences between the extreme distribution of all the temperature data at each temperature measuring point and its respective homologous measuring points are compared respectively before the current time, and the temperature synchronization degree of each temperature measuring point at each collection time point is evaluated;

[0008] analyzing the autocorrelation degree of all temperature data in the neighborhood of each collection time, the similarity between each temperature measurement point and each of its homologous measurement points, determining the temperature correlation degree of each temperature measurement point at each collection time, and combining the temperature synchronization degree to obtain the temperature interference degree of each temperature measurement point at each collection time;

[0009] comparing the change trend of all displacement data of the main shaft of the numerical control machine tool in each direction to determine the main direction of the main shaft of the numerical control machine tool, synthesizing the temperature interference degree of any homologous measurement point of each temperature measurement point at all collection times to obtain the reliability of any homologous measurement point of each temperature measurement point, and combining the correlation degree between the displacement data of the main shaft of the numerical control machine tool in the main direction and the temperature data of any homologous measurement point of each temperature measurement point at all collection times to construct the temperature sensitivity of each temperature measurement point at the current time; and determining the temperature weight coefficient of each temperature measurement point at the current time based on the temperature interference degree and the temperature sensitivity.

[0010] Based on the temperature data and the temperature weight coefficient of each temperature measurement point at the current time, the temperature of the numerical control machine tool at the current time is compensated.

[0011] Preferably, the expression of the temperature synchronization degree of each temperature measurement point at each collection time is: In the formula, S i,j represents the temperature synchronization degree of the jth temperature measurement point at the ith collection time; g i,j represents the mean difference between the temperature data of all collection times in the neighborhood of the ith collection time at the jth temperature measurement point and all its homologous measurement points; h i,j represents the mean difference between the range of temperature data of all collection times in the neighborhood of the ith collection time at the jth temperature measurement point and all its homologous measurement points; exp() represents the exponential function with natural constant as the base.

[0012] Preferably, the determination method of the temperature correlation degree of each temperature measurement point at each collection time is:

[0013] obtaining the autocorrelation sequence of the temperature data of each temperature measurement point at all collection times in the neighborhood of each collection time, denoted as the autocorrelation sequence of each temperature measurement point at each collection time;

[0014] calculating the mean value of the similarity between the autocorrelation sequences of each temperature measurement point and all its homologous measurement points at each collection time as the temperature correlation degree of each temperature measurement point at each collection time.

[0015] Preferably, the temperature interference degree of each temperature measurement point at each collection time is the reciprocal of the mean value of the temperature synchronization degree and the temperature correlation degree of each temperature measurement point at each collection time.

[0016] Preferably, the method for determining the main direction of the spindle of the numerical control machine tool is as follows:

[0017] The displacement data of the spindle of the numerical control machine tool at all collection time points in each direction is fitted to obtain a fitting straight line of the spindle of the numerical control machine tool in each direction, and the absolute value of the slope of the fitting straight line in all directions is calculated. The direction with the maximum absolute value of the slope is taken as the main direction of the spindle of the numerical control machine tool.

[0018] Preferably, the reliability of any homologous measuring point of each temperature measuring point is the normalized value of the reciprocal of the cumulative sum of the temperature interference degrees of all collection time points of any homologous measuring point of each temperature measuring point.

[0019] Preferably, the expression of the temperature sensitivity of each temperature measuring point at the current time point is as follows: In the formula, D j represents the temperature sensitivity of the temperature measuring point j at the current time point; Ph j,z represents the reliability of the zth homologous measuring point of the temperature measuring point j; dh j,z represents the correlation degree between the displacement data of the spindle of the numerical control machine tool in the main direction at all collection time points before the current time point and the temperature data of the zth homologous measuring point of the temperature measuring point j; Z j represents the number of all homologous measuring points of the temperature measuring point j.

[0020] Preferably, the method for determining the temperature weight coefficient of each temperature measuring point at the current time point is as follows:

[0021] The average value of the temperature interference degrees of each temperature measuring point at all collection time points before the current time point is calculated, and the ratio of the temperature sensitivity to the average value of the temperature interference degrees is taken as the normalized value, which is taken as the temperature weight coefficient of each temperature measuring point at the current time point.

[0022] Preferably, the temperature compensation of the numerical control machine tool at the current time point comprises:

[0023] The expression of the temperature compensation data R of the numerical control machine tool at the current time point is as follows: In the formula, a j represents the temperature data of the jth temperature measuring point at the current time point; Q j represents the temperature weight coefficient of the jth temperature measuring point at the current time point; N represents the number of all temperature measuring points on the numerical control machine tool.

[0024] In the second aspect, the embodiments of the present application also provide a data-driven numerical control machine tool temperature compensation system, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the data-driven numerical control machine tool temperature compensation method in any of the above embodiments when executing the computer program.

[0025] The application has at least the following beneficial effects:

[0026] The application can more accurately evaluate the degree of noise interference on the temperature data of each temperature measuring point by analyzing the differences in change trend and amplitude between the temperature data of the temperature measuring point and its homologous measuring point, and combining the similarity between the autocorrelation degree of the temperature data of the temperature measuring point and its homologous measuring point, which helps to reduce the influence of noise data on the evaluation of thermal deformation error of the temperature measuring point, thereby improving the precision of temperature compensation of the numerical control machine tool; further, by analyzing the correlation between the displacement data of the numerical control machine tool and the temperature data of the temperature measuring point, and combining the temperature interference degree, the temperature sensitivity is constructed, which reflects the sensitive degree of the temperature measuring point to the thermal deformation error of the numerical control machine tool, which helps to identify the temperature measuring point which has greater influence on the thermal deformation error, and can more comprehensively evaluate the sensitive degree of the temperature measuring point, thereby improving the accuracy of temperature compensation of the numerical control machine tool; further, the temperature weight coefficient is constructed by comprehensively considering the temperature interference degree and the temperature sensitivity, which is the influence degree of each temperature measuring point data on the thermal deformation error of the numerical control machine tool, which helps to determine the temperature measuring point which is most critical to temperature compensation, and more effectively compensates the temperature of the numerical control machine tool, thereby improving the accuracy of temperature compensation of the numerical control machine tool. The data-driven temperature compensation method can more accurately compensate the thermal deformation error of the numerical control machine tool, thereby improving the precision of temperature compensation of the numerical control machine tool. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed in the following embodiment or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0028] Figure 1 A step flow chart of a data-driven numerical control machine tool temperature compensation method provided by an embodiment of the present application is provided.

[0029] Figure 2 A temperature interference degree acquisition process schematic diagram provided by an embodiment of the present application is provided.

[0030] Figure 3 A temperature weight coefficient extraction framework schematic diagram provided by an embodiment of the present application is provided. DETAILED DESCRIPTION

[0031] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined object, the specific implementation, structure, features and effects of the data-driven temperature compensation method and system for a numerical control machine tool according to the present application are described in detail as follows in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0033] The specific scheme of the data-driven temperature compensation method and system for a numerical control machine tool provided by the present application is described in detail below in combination with the drawings.

[0034] Please refer to Figure 1 which shows the step flowchart of the data-driven temperature compensation method for a numerical control machine tool provided by one embodiment of the present application, which includes the following steps:

[0035] Step S1: setting multiple temperature measuring points on the numerical control machine tool, acquiring the temperature data of each temperature measuring point at all collection time points within a preset time length before the current time, and the displacement data of the main shaft of the numerical control machine tool in each direction.

[0036] N temperature measuring points are set in the numerical control machine tool, temperature sensors are used to collect the temperature data of each temperature measuring point at all collection time points within a preset time length t before the current time, and displacement sensors are used to collect the displacement data of the main shaft of the numerical control machine tool in X, Y and Z directions within the preset time length t before the current time, wherein the data collection frequency is set to f, the X direction represents the forward direction parallel to the main shaft, the Y direction represents the transverse movement direction parallel to the main console and perpendicular to the forward direction, and the Z direction represents the upward and downward movement direction perpendicular to the main console.

[0037] It should be noted that the number N of temperature measuring points, the preset time length t, and the data collection frequency f are all artificially set. In the present embodiment, the number N of temperature measuring points is 20, the preset time length t is 5 minutes, and the data collection frequency f is 10 Hz. The implementer can also set them according to the specific situation, and the present embodiment does not make special limitations.

[0038] Step S2: Clustering all temperature measuring points, recording all temperature measuring points in the cluster cluster where each temperature measuring point is, as the homologous measuring points of each temperature measuring point, comparing the difference between each temperature measuring point and its each homologous measuring point of all temperature data in the neighborhood at each collection time before the current time, and the difference between the extreme distribution of all temperature data at each temperature measuring point and its each homologous measuring point, to evaluate the temperature synchronization degree of each temperature measuring point at each collection time; analyzing the similarity between the autocorrelation degree of all temperature data in the neighborhood at each collection time at each temperature measuring point and its each homologous measuring point, to determine the temperature correlation degree of each temperature measuring point at each collection time, and combining the temperature synchronization degree, to obtain the temperature interference degree of each temperature measuring point at each collection time.

[0039] Since the heat source of the numerical control machine tool mainly comes from the motor, thermal friction, cooling liquid and environmental temperature, etc., the temperature change of different positions of the numerical control machine tool is usually the result of thermal coupling of multiple heat sources. For temperature measuring points with similar thermal coupling results, their temperature changes usually show synchronization in time, that is, in the same time period, these temperature measuring points have similar temperature change trend and amplitude, and their temperature data usually have similar autocorrelation distribution in time. When the temperature data collected by the temperature measuring point at a certain time is disturbed by noise, due to the randomness of the noise, the synchronization and autocorrelation distribution are usually destroyed. Therefore, in order to improve the accuracy of evaluating the influence degree of the temperature data of a certain temperature measuring point on the thermal deformation error of the numerical control machine tool, the temperature interference degree of each temperature measuring point at each collection time is evaluated by comparing the difference between the temperature data change trend and amplitude at the temperature measuring point and its homologous measuring point, and combining the similarity between the autocorrelation degree of the temperature data at the temperature measuring point and the homologous measuring point, which is:

[0040] (1) Clustering all temperature measuring points on the numerical control machine tool, wherein the DTW distance of the temperature data of all collection times between different temperature measuring points is used as the clustering distance, to obtain a plurality of cluster clusters, and all temperature measuring points in the cluster cluster where each temperature measuring point is are recorded as the homologous measuring points of each temperature measuring point.

[0041] It should be noted that there are many commonly used clustering algorithms, and in the present embodiment, the k-means clustering algorithm is used to cluster all temperature measuring points at the current time, and the implementer can also use other clustering methods such as DPC density mean clustering. The selection of the clustering method is not specially limited in the present embodiment.

[0042] Wherein, the clustering principle of k-means clustering algorithm and the calculation process of DTW are all known technologies, and the specific clustering process and calculation process will not be repeated.

[0043] (2) Further, before the current time, for each temperature measuring point, a neighborhood W is divided with each collection time as the center, wherein the radius of the neighborhood W is artificially set, and in the embodiment, the radius of the neighborhood W is 7, and the implementer can set it according to the specific situation, and the embodiment does not have special limitations.

[0044] (3) Further, before the current time, the differences between all temperature data in the neighborhood of each collection time and the extreme distribution thereof between each temperature measuring point and each homologous measuring point thereof are compared respectively, the temperature synchronization degree of each temperature measuring point at each collection time is evaluated, and specifically, the temperature synchronization degree S of the jth temperature measuring point at the ith collection time is calculated according to the following formula:

[0045] i,j The expression of the temperature synchronization degree S of the jth temperature measuring point at the ith collection time is as follows: In the formula, g i,j represents the average of the differences between the temperature data of all collection times in the neighborhood of the ith collection time between the jth temperature measuring point and all homologous measuring points thereof; h i,j represents the average of the differences between the range of the temperature data of all collection times in the neighborhood of the ith collection time between the jth temperature measuring point and all homologous measuring points thereof; and exp() represents an exponential function with a natural constant as the base.

[0046] According to the temperature synchronization degree of each temperature measuring point at each collection time, if the average of the differences between the temperature data of all collection times in the neighborhood of the ith collection time between the jth temperature measuring point and all homologous measuring points thereof is larger, it indicates that the similarity of the temperature change trend between the jth temperature measuring point and the homologous measuring points thereof is smaller, and if the average of the differences between the range of the temperature data of all collection times in the neighborhood of the ith collection time between the jth temperature measuring point and all homologous measuring points thereof is larger, it indicates that the difference of the temperature amplitude between the jth temperature measuring point and the homologous measuring points thereof is larger, and the temperature synchronization degree is smaller.

[0047] On the contrary, if the average of the differences between the temperature data of all collection times in the neighborhood of the ith collection time between the jth temperature measuring point and all homologous measuring points thereof is smaller, and the average of the differences between the range of the temperature data of all collection times in the neighborhood of the ith collection time between the jth temperature measuring point and all homologous measuring points thereof is smaller, it indicates that the difference of the temperature amplitude between the jth temperature measuring point and the homologous measuring points thereof is smaller, and the temperature synchronization degree is larger.

[0048] (4) Further, the autocorrelation sequence of the temperature data of each temperature measuring point at all collection times in the neighborhood of each collection time is obtained as the autocorrelation sequence of each temperature measuring point at each collection time.

[0049] The autocorrelation sequence is obtained by a known technology, and the specific obtaining process is not described again.​

[0050] The average of the similarity of the autocorrelation sequence between each temperature measuring point and all of its homologous measuring points at each acquisition time is calculated as the temperature correlation degree of each temperature measuring point at each acquisition time.

[0051] It should be noted that there are many methods for measuring the similarity between sequences. In the embodiment, the cosine similarity of the autocorrelation sequence between each temperature measuring point and all of its homologous measuring points at each acquisition time is calculated to measure the similarity degree of the autocorrelation sequence between the temperature measuring point and its homologous measuring points. The implementer can also use other methods for measuring the similarity between sequences, such as the Jaccard similarity coefficient or the reciprocal of the Euclidean distance. The selection of the method for measuring the similarity between sequences is not particularly limited in the embodiment.

[0052] The calculation process of the cosine similarity is a known technology, and the specific calculation steps are not described again.

[0053] (5) Further, the reciprocal of the average of the temperature synchronization degree and the temperature correlation degree of each temperature measuring point at each acquisition time before the current time is taken as the temperature interference degree of each temperature measuring point at each acquisition time.

[0054] According to the temperature interference degree of each temperature measuring point at each acquisition time, if the temperature correlation degree is larger, it indicates that the similarity between the autocorrelation of the temperature measuring point and its homologous measuring points is larger, i.e., the similarity between the temperature change trends of the temperature measuring point and the homologous measuring points is larger, which indicates that the influence of the noise on the thermal deformation error of the numerical control machine tool is smaller, and the possibility of being disturbed by the noise is smaller. Moreover, the larger the temperature synchronization degree is, the larger the similarity between the temperature change trends of the temperature measuring point and the homologous measuring points is, and the smaller the finally obtained temperature interference degree is, which indicates that the influence of the noise on the thermal deformation error of the numerical control machine tool is smaller.

[0055] On the contrary, if the temperature correlation degree is smaller, it indicates that the similarity between the autocorrelation of the temperature measuring point and its homologous measuring points is smaller, i.e., the similarity between the temperature change trends of the temperature measuring point and the homologous measuring points is smaller, which indicates that the influence of the noise on the thermal deformation error of the numerical control machine tool is larger, and the possibility of being disturbed by the noise is larger. Moreover, the smaller the temperature synchronization degree is, the smaller the similarity between the temperature change trends of the temperature measuring point and the homologous measuring points is, and the larger the finally obtained temperature interference degree is, which indicates that the influence of the noise on the thermal deformation error of the numerical control machine tool is larger.

[0056] Preferably, the temperature interference degree acquisition process provided by the embodiment is shown in the schematic diagram as Figure 2 .

[0057] Step S3: comparing the change trend of all displacement data of the spindle of the numerical control machine tool in each direction, determining the main direction of the spindle of the numerical control machine tool; synthesizing the temperature interference degree of any homologous measuring point of each temperature measuring point at all collection time points, obtaining the reliability of any homologous measuring point of each temperature measuring point, and combining the correlation degree between the displacement data of the spindle of the numerical control machine tool in the main direction and the temperature data of any homologous measuring point of each temperature measuring point at all collection time points, constructing the temperature sensitivity of each temperature measuring point at the current time; based on the temperature interference degree and the temperature sensitivity, determining the temperature weight coefficient of each temperature measuring point at the current time.

[0058] (1) First, since the thermal deformation error of the numerical control machine tool is usually the comprehensive influence result of the thermal deformation of each position thereof, in order to improve the evaluation accuracy of the sensitivity of each temperature measuring point of the numerical control machine tool to the influence of the thermal deformation error of the numerical control machine tool, the displacement data of the spindle of the numerical control machine tool at all collection time points in each direction is fitted to obtain the fitting straight line of the spindle of the numerical control machine tool in each direction, and the absolute value of the slope of the fitting curve of the spindle of the numerical control machine tool in all directions is calculated, the direction with the maximum absolute value of the slope is recorded as the main direction.

[0059] It should be noted that the direction with the maximum absolute value of the slope is taken as the main direction because the displacement change caused by temperature change is most significant in the direction with the maximum absolute value of the slope, i.e. the direction is most sensitive to temperature change, therefore, the overall influence accuracy of the thermal deformation of the direction on the numerical control machine tool is the largest, and thus the influence degree of the thermal deformation of the direction on the temperature compensation is analyzed.

[0060] (2) Secondly, in the numerical control machine tool, the sensitivity of temperature measuring points with similar heat source coupling results to the thermal deformation error of the numerical control machine tool is usually close. Therefore, the correlation degree between the displacement data of the numerical control machine tool and the temperature data of the homologous measuring points of each temperature measuring point is analyzed, and the temperature sensitivity of each temperature measuring point at the current time is determined in combination with the temperature interference degree, specifically:

[0061] the cumulative sum of the temperature interference degree of any homologous measuring point of each temperature measuring point at all collection time points is calculated, and the normalized value of the reciprocal of the cumulative sum is taken as the reliability of any homologous measuring point of each temperature measuring point;

[0062] Further, based on the correlation degree between the displacement data of the spindle of the numerical control machine tool in the main direction and the temperature data of any homologous measuring point of each temperature measuring point at all collection time points, and in combination with the reliability, the temperature sensitivity of each temperature measuring point at the current time is determined, specifically:

[0063] The expression of the temperature sensitivity D j of the jth temperature measuring point at the current time is: wherein Ph j,z represents the reliability of the zth homologous measuring point of the temperature measuring point j; dh j,z represents the correlation degree between the displacement data of the main shaft of the numerical control machine tool in the main direction at all collection time points before the current time and the temperature data of the zth homologous measuring point of the jth temperature measuring point; Z j represents the number of all homologous measuring points of the temperature measuring point j.

[0064] It should be noted that there are many methods for measuring the correlation degree between data sets. In the embodiment, the Pearson correlation coefficient between the displacement data and the temperature data is calculated to measure the correlation degree between the displacement data and the temperature data. The implementer can also use other methods for measuring the correlation degree between data sets, such as the Kendall correlation coefficient or the Spearman correlation coefficient. The selection of the method for measuring the correlation degree between data sets is not particularly limited in the embodiment.

[0065] The calculation process of the Pearson correlation coefficient is a known technology, and the specific calculation steps are not described again.

[0066] Further, according to the temperature sensitivity of each temperature measuring point at the current time, if the reliability of the zth homologous measuring point of the jth temperature measuring point is greater, it indicates that the sensitivity of the jth temperature measuring point to the thermal deformation error of the numerical control machine tool is more reliable, and this sensitivity can better represent the sensitivity of other temperature measuring points with similar heat source influence to the thermal deformation error of the numerical control machine tool. The greater the correlation degree between the displacement data and the temperature data, the more similar the change trend between the displacement data and the temperature data, and the greater the temperature sensitivity, the greater the sensitivity of the jth temperature measuring point to the thermal deformation error of the numerical control machine tool.

[0067] On the contrary, if the reliability of the zth homologous measuring point of the jth temperature measuring point is greater, it indicates that the sensitivity of the jth temperature measuring point to the thermal deformation error of the numerical control machine tool is smaller. The smaller the correlation degree between the displacement data and the temperature data, the smaller the similarity of the change trend between the displacement data and the temperature data, and the smaller the temperature sensitivity, the smaller the sensitivity of the jth temperature measuring point to the thermal deformation error of the numerical control machine tool.

[0068] (3) Then, based on the temperature interference degree and the temperature sensitivity, the temperature weight coefficient of each temperature measuring point at the current time is determined, specifically:

[0069] The average of the temperature interference degree of all the temperature data collected at each temperature measuring point before the current time is calculated, and the ratio of the temperature sensitivity to the average of the temperature interference degree is normalized to a value, which is taken as the temperature weight coefficient of each temperature measuring point at the current time.

[0070] According to the temperature weight coefficient of each temperature measuring point at the current time, it can be understood that the greater the temperature sensitivity of the temperature measuring point to the thermal deformation error of the CNC machine tool, and the smaller the average of the temperature interference degree of the temperature measuring point, the more the temperature data at the current time can reflect the thermal deformation of the CNC machine tool at the current time, and the greater the temperature weight coefficient of the temperature measuring point, and the more the temperature data of the temperature measuring point at the current time can reflect the thermal deformation of the CNC machine tool at the current time.

[0071] On the contrary, the smaller the temperature sensitivity of the temperature measuring point to the thermal deformation error of the CNC machine tool, and the greater the average of the temperature interference degree of the temperature measuring point, the less the temperature data at the current time can reflect the thermal deformation of the CNC machine tool at the current time, and the smaller the temperature weight coefficient of the temperature measuring point, and the less the temperature data of the temperature measuring point at the current time can reflect the thermal deformation of the CNC machine tool at the current time.

[0072] Preferably, the temperature weight coefficient extraction framework provided by the embodiment is shown in Figure 3 .

[0073] Step S4: Based on the temperature data and the temperature weight coefficient of each temperature measuring point at the current time, the temperature of the CNC machine tool at the current time is compensated.

[0074] Based on the temperature weight coefficient obtained in step S3, the temperature of the CNC machine tool at the current time is compensated based on the temperature weight coefficient and the temperature data of all the temperature measuring points at the current time, specifically:

[0075] The expression of the temperature compensation data R of the CNC machine tool at the current time is: In the formula, a j represents the temperature data of the jth temperature measuring point at the current time; Q j represents the temperature weight coefficient of the jth temperature measuring point at the current time; N represents the number of all temperature measuring points on the CNC machine tool.

[0076] So far, by analyzing the distribution characteristics of the temperature data between the temperature measuring points with similar heat source coupling results in the numerical control machine tool, the temperature interference degree is constructed, which can more accurately distinguish the noise interference degree of the temperature data of each temperature measuring point of the numerical control machine tool; by analyzing the sensitive degree of the temperature measuring points with similar heat source coupling results in the numerical control machine tool to the thermal deformation error of the numerical control machine tool, and combining the correlation degree between the temperature data and the displacement data and the noise interference degree, the temperature sensitivity is constructed, which can more accurately evaluate the evaluation accuracy of the sensitive degree of each temperature measuring point in the numerical control machine tool to the thermal deformation error of the numerical control machine tool; finally, the temperature weight coefficient is constructed by comprehensively considering the temperature sensitivity and the temperature interference degree, and the temperature compensation result of the numerical control machine tool is calculated according to the temperature weight coefficient, which reduces the method for calculating the temperature compensation result in the traditional numerical control machine tool, which does not consider the different effects of temperature changes at different positions in the numerical control machine tool on the thermal deformation of the machine tool, and the interference of external noise on the temperature data in the collection process, which can more accurately calculate the temperature compensation result of the numerical control machine tool, and then realize more accurate control of the motion of the numerical control machine tool.

[0077] Based on the same inventive concept as the above method, the embodiments of the present application also provide a data-driven numerical control machine tool temperature compensation system, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above data-driven numerical control machine tool temperature compensation methods when executing the computer program.

[0078] It should be noted that the above-mentioned embodiments of the present application are only for description, not representing the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or may be advantageous.

[0079] Each embodiment in the present specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the differences from other embodiments.

[0080] The above is only the preferred embodiment of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A data-driven temperature compensation method for a computer numerical control machine, characterized in that, The method comprises the following steps: Setting multiple temperature measuring points on the numerical control machine tool, obtaining temperature data of each temperature measuring point at all collection time points within a preset time length before the current time and displacement data of the main shaft of the numerical control machine tool in each direction; Clustering all temperature measuring points, recording all temperature measuring points in the cluster cluster where each temperature measuring point is as homologous measuring points of each temperature measuring point, comparing differences between each temperature measuring point and its respective homologous measuring points of all temperature data in the neighborhood of each collection time point before the current time, and differences between each temperature measuring point and its respective homologous measuring points of extreme distribution of all temperature data, evaluating temperature synchronization degree of each temperature measuring point at each collection time point; Analyzing similarity between each temperature measuring point and its respective homologous measuring points of autocorrelation degree of all temperature data in the neighborhood of each collection time point, determining temperature correlation degree of each temperature measuring point at each collection time point, and obtaining temperature interference degree of each temperature measuring point at each collection time point in combination with the temperature synchronization degree, the temperature interference degree of each temperature measuring point at each collection time point is the reciprocal of the mean value of the temperature synchronization degree and the temperature correlation degree of each temperature measuring point at each collection time point; the determination method of the temperature correlation degree of each temperature measuring point at each collection time point is: obtaining autocorrelation sequence of temperature data of each temperature measuring point at all collection time points in the neighborhood of each collection time point, recording as autocorrelation sequence of each temperature measuring point at each collection time point; calculating the mean value of the similarity between the autocorrelation sequence of each temperature measuring point and all its homologous measuring points as the temperature correlation degree of each temperature measuring point at each collection time point; The trend of all displacement data of the spindle of the numerical control machine tool in each direction is compared to determine the direction of the spindle of the numerical control machine tool. The method for determining the direction of the spindle of the numerical control machine tool is as follows: fitting the displacement data of the spindle of the numerical control machine tool at all collection time points in each direction to obtain a fitting straight line of the spindle of the numerical control machine tool in each direction, and calculating the absolute value of the slope of the fitting straight line in all directions. The direction with the largest absolute value of the slope is taken as the direction of the spindle of the numerical control machine tool. The reliability of any homologous measuring point of each temperature measuring point is obtained by comprehensively considering the temperature interference degree of the homologous measuring point at all collection time points before the current time. The temperature sensitivity of each temperature measuring point at the current time is constructed by combining the correlation between the displacement data of the spindle of the numerical control machine tool in the direction and the temperature data of any homologous measuring point of each temperature measuring point at all collection time points. The reliability of any homologous measuring point of each temperature measuring point is the normalized value of the reciprocal of the cumulative sum of the temperature interference degree of the homologous measuring point of each temperature measuring point at all collection time points. Based on the temperature interference degree and the temperature sensitivity, the temperature weight coefficient of each temperature measuring point at the current time is determined. The method for determining the temperature weight coefficient of each temperature measuring point at the current time is as follows: calculating the mean value of the temperature interference degree of each temperature measuring point at all collection time points before the current time, and taking the ratio of the temperature sensitivity to the mean value of the temperature interference degree as the normalized value, as the temperature weight coefficient of each temperature measuring point at the current time. The temperature of the numerical control machine tool at the current time is compensated based on the temperature data and the temperature weight coefficient of each temperature measuring point at the current time. The temperature sensitivity satisfies the following formula: ； wherein, represents the temperature sensitivity of the temperature measurement point j at the current time point, represents the reliability of the zth homologous measurement point of the temperature measurement point j, represents the correlation degree between the displacement data of the main shaft of the numerical control machine tool in the direction and the temperature data of the zth homologous measurement point of the temperature measurement point j at all collection time points before the current time point, represents the number of all homologous measurement points of the temperature measurement point j; The expression of the temperature synchronization degree of each temperature measuring point at each collection time is: ; wherein, represents the temperature synchronization degree of the jth temperature measuring point at the ith collection time; represents the mean value of the difference between the jth temperature measuring point and all its homologous measuring points of the temperature data of all collection times in the neighborhood of the ith collection time; represents the mean value of the difference between the jth temperature measuring point and all its homologous measuring points of the range of the temperature data of all collection times in the neighborhood of the ith collection time; and exp() represents an exponential function with a natural constant as the base number.

2. A data-driven temperature compensation method for a CNC machine tool as claimed in claim 1, wherein, The compensation of the temperature of the numerical control machine tool at the current time includes: Temperature compensation data of a numerical control machine tool at a current time The expression is: ; in the formula, represents the temperature data of the jth temperature measuring point at the current time; represents the temperature weight coefficient of the jth temperature measuring point at the current time; N represents the number of all temperature measuring points on the numerical control machine tool.

3. A data-driven temperature compensation system for a computer numerical control machine, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein, The processor implements the steps of the data-driven temperature compensation method of the numerical control machine tool according to claim 1 or 2 when executing the computer program. The processor implements the steps of the data-driven temperature compensation method of the numerical control machine tool according to claim 1 or 2 when executing the computer program.

Images